{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KDYYQEFMCLVNTXEEXSN67WCYS5","short_pith_number":"pith:KDYYQEFM","schema_version":"1.0","canonical_sha256":"50f18810ac12ead9dc84bc9befd8589744d79f873011c1669ec914e9da75fa2b","source":{"kind":"arxiv","id":"1909.03835","version":3},"attestation_state":"computed","paper":{"title":"Data Sanity Check for Deep Learning Systems via Learnt Assertions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haochuan Lu, Huanlin Xu, Nana Liu, Xin Wang, Yangfan Zhou","submitted_at":"2019-09-06T10:15:21Z","abstract_excerpt":"Reliability is a critical consideration to DL-based systems. But the statistical nature of DL makes it quite vulnerable to invalid inputs, i.e., those cases that are not considered in the training phase of a DL model. This paper proposes to perform data sanity check to identify invalid inputs, so as to enhance the reliability of DL-based systems. We design and implement a tool to detect behavior deviation of a DL model when processing an input case. This tool extracts the data flow footprints and conducts an assertion-based validation mechanism. The assertions are built automatically, which ar"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1909.03835","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-06T10:15:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0e8f25562ba12cc3057295f1356c2f84b8199045cd9565ff26744aab1d5e8bc6","abstract_canon_sha256":"c1679c62fd3780a4d9f04f91bcd81f67d783da050abd121e22b9dfd3963ce392"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:53.051153Z","signature_b64":"zkLC31oCDCxm1uUtOT6sjCIyjoexTiUTxKqdDhvrSolBJM/zpHvp0KwKTzN9QLcluZjPhjwsvFjyzJazMm8OBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50f18810ac12ead9dc84bc9befd8589744d79f873011c1669ec914e9da75fa2b","last_reissued_at":"2026-07-05T00:07:53.050670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:53.050670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Sanity Check for Deep Learning Systems via Learnt Assertions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haochuan Lu, Huanlin Xu, Nana Liu, Xin Wang, Yangfan Zhou","submitted_at":"2019-09-06T10:15:21Z","abstract_excerpt":"Reliability is a critical consideration to DL-based systems. But the statistical nature of DL makes it quite vulnerable to invalid inputs, i.e., those cases that are not considered in the training phase of a DL model. This paper proposes to perform data sanity check to identify invalid inputs, so as to enhance the reliability of DL-based systems. We design and implement a tool to detect behavior deviation of a DL model when processing an input case. This tool extracts the data flow footprints and conducts an assertion-based validation mechanism. The assertions are built automatically, which ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03835","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.03835/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1909.03835","created_at":"2026-07-05T00:07:53.050727+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.03835v3","created_at":"2026-07-05T00:07:53.050727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03835","created_at":"2026-07-05T00:07:53.050727+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDYYQEFMCLVN","created_at":"2026-07-05T00:07:53.050727+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDYYQEFMCLVNTXEE","created_at":"2026-07-05T00:07:53.050727+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDYYQEFM","created_at":"2026-07-05T00:07:53.050727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KDYYQEFMCLVNTXEEXSN67WCYS5","json":"https://pith.science/pith/KDYYQEFMCLVNTXEEXSN67WCYS5.json","graph_json":"https://pith.science/api/pith-number/KDYYQEFMCLVNTXEEXSN67WCYS5/graph.json","events_json":"https://pith.science/api/pith-number/KDYYQEFMCLVNTXEEXSN67WCYS5/events.json","paper":"https://pith.science/paper/KDYYQEFM"},"agent_actions":{"view_html":"https://pith.science/pith/KDYYQEFMCLVNTXEEXSN67WCYS5","download_json":"https://pith.science/pith/KDYYQEFMCLVNTXEEXSN67WCYS5.json","view_paper":"https://pith.science/paper/KDYYQEFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.03835&json=true","fetch_graph":"https://pith.science/api/pith-number/KDYYQEFMCLVNTXEEXSN67WCYS5/graph.json","fetch_events":"https://pith.science/api/pith-number/KDYYQEFMCLVNTXEEXSN67WCYS5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDYYQEFMCLVNTXEEXSN67WCYS5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDYYQEFMCLVNTXEEXSN67WCYS5/action/storage_attestation","attest_author":"https://pith.science/pith/KDYYQEFMCLVNTXEEXSN67WCYS5/action/author_attestation","sign_citation":"https://pith.science/pith/KDYYQEFMCLVNTXEEXSN67WCYS5/action/citation_signature","submit_replication":"https://pith.science/pith/KDYYQEFMCLVNTXEEXSN67WCYS5/action/replication_record"}},"created_at":"2026-07-05T00:07:53.050727+00:00","updated_at":"2026-07-05T00:07:53.050727+00:00"}